Cross Sell Opportunity Finder

Purpose

Finds products that are almost always purchased alone (single-item orders) and identifies potential cross-sell partners based on category affinity, price complementarity, and customer overlap. While frequently-bought-together finds existing patterns, this skill finds MISSING patterns — products that SHOULD be cross-sold but aren't. Read-only — no mutations.

Prerequisites

Parameters

Safety

> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time.

Workflow Steps

Inputs: query: "created_at:>=''", first: 250, select lineItems { product { id, title, productType, vendor }, quantity, originalTotalSet }, pagination cursor

Expected output: All orders with product data

Inputs: Product IDs for solo items and potential partners

Expected output: Product type, vendor, price, collections for affinity matching

GraphQL Operations

# orders:query — validated against api_version 2025-01
query OrdersForCrossSell($query: String!, $after: String) {
  orders(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        customer { id }
        lineItems(first: 50) {
          edges {
            node {
              product { id title productType vendor }
              quantity
              originalTotalSet { shopMoney { amount currencyCode } }
            }
          }
        }
      }
    }
    pageInfo { hasNextPage endCursor }
  }
}

# products:query — validated against api_version 2025-01
query ProductEnrichment($ids: [ID!]!) {
  nodes(ids: $ids) {
    ... on Product {
      id
      title
      productType
      vendor
      priceRangeV2 {
        minVariantPrice { amount currencyCode }
      }
      totalInventory
      status
    }
  }
}

Session Tracking

Claude MUST emit the following output at each stage. This is mandatory.

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Cross-Sell Opportunity Finder        ║
║  Store: <store domain>                       ║
║  Started: <YYYY-MM-DD HH:MM UTC>             ║
╚══════════════════════════════════════════════╝

After each step, emit:

[N/TOTAL] <QUERY|MUTATION>  <OperationName>
          → Params: <brief summary of key inputs>
          → Result: <count or outcome>

On completion, emit:

For format: human (default):

══════════════════════════════════════════════
CROSS-SELL OPPORTUNITY REPORT  (<days_back> days)
  Products analyzed:         <n>
  High solo-rate products:   <n>
  ─────────────────────────────
  TOP CROSS-SELL OPPORTUNITIES:

  "<product A>"  (solo rate: <pct>%, <n> orders)
    → Suggested partner: "<product B>" (same vendor, complementary type)
    → Price fit: $<main> + $<partner> = $<combined>
    → Potential AOV lift: +$<amount> per order

  Revenue opportunity: $<total> (if <pct>% of solo orders add partner)

  Output: cross_sell_opportunities_<date>.csv
══════════════════════════════════════════════

Output Format

CSV file cross_sell_opportunities_.csv with columns:

product_id, product_title, total_orders, solo_orders, solo_rate, suggested_partner_id, suggested_partner_title, affinity_type, potential_aov_lift

Error Handling

Best Practices